Professional Documents
Culture Documents
Akrit Mudvari, Student Member, IEEE and Taikang Ning, Senior Member, IEEE
e k x ( k ) a1 x ( k 1) a 2 x ( k 2 ) (1)
Similarly, IMmovement is calculated with 1 for x<µmovement.
AR model coefficients {a1, a2} are estimated using a short
data segment and the respiration rate is estimated by B. Membership Function Using Peak Average of ‘normal’
and ‘movement artifact’:
2
f samp 4 a 2 a1 Once the respiration rates for signals classified as ‘normal’
). (2)
1
freq tan ( and as ‘affected with movement’ are obtained, membership
2 a1
functions are heuristically assigned (the assignment emulated
where fsamp is the sampling frequency used during respiration decision-making of the experts and was later statistically
measurement. verified). Table I. shows the example of assigned
Since the normal breath signals were found to exhibit membership function values.
regular behavior similar to a sinusoidal signal while body
movement artifacts displayed irregular fluctuations, the 2nd
order AR model refection coefficient (a2) can be used to TABLE I: ASSIGNED MEMBERSHIP FUNCTIONS OF NORMAL RESPIRATION AND
signify the closeness to a sine wave, where the magnitude of MOTION ARTIFACTS
a2 closer to 1 indicates a regular waveform.
Motion Peaks Normal Respiration Peaks
0 1 2 3 4
III. FUZZY LOGIC APPROACH
0 0 0.1 0.6 0.9 1
A Fuzzy-logic [9] based approach is used in our study to
1 0 0.1 0.5 0.85 0.96
analyze respiration signals. We developed membership
functions that assign varying degrees of membership to the 2 0 0.1 0.45 0.85 0.93
variables that are used in decision-making [9]. The first input
3 0 0.07 0.45 0.83 0.88
variable used in the calculation is the relative magnitude of
the dominant frequency obtained from autoregressive >=4 0 0.05 0.35 0.8 0.85
modelling. For the second input, average of healthy peaks
detected using adaptive threshold method, zero crossing
method and respiration waveform slope method are used.
2819
Figure 3: Detection of apnea (apnea is signified by a lack of signal Fig 4: Detection of episodes of body movement (noisy signal).
strength). The program increases the amplitude (of dashed line in the Detection of such episodes is shown by horizontal line with non-zero
figure) to about 180 when apnea episode is detected. amplitude (~50).
IV. RESULTS AND DISCUSSION caused by body movements was characterized by a lack of
To examine the performance of the proposed algorithm, signal regularity, inconsistency in frequency and amplitude
respiration signals measured by an abdominal strain gauge recording, and a sudden change of the waveform. To classify
were used [4] with a sampling rate of 20 Hz. Respiratory such waveforms, fuzzy logic-based decision making was
measurements were classified as ‘breathing with instances of used. Fig. 4 shows a set of signals resulting from body
apnea’, ‘normal breathing’ and ‘breathing with body movements, and our algorithm was able to correctly
movement’. The algorithm was designed to process categorize these instances as body movements. In case of the
respiratory data in short segments of duration of 10 seconds body movements, our fuzzy-logic based heuristic
or 15 seconds. Each short segment will be categorized classification algorithm achieved more than 90% agreement
according to the extracted respiration features. with human experts. In case of episodes where the human
judgment and the fuzzy logic based algorithm differed, the
Apnea is characterized by a lack of breathing for a period input membership functions for “normal breathing” and
of 10 seconds or longer; an average of 25 seconds was noted “instances of body movement” were found to be very close to
in the literature [3]. In our algorithm, we used an interval of each other. Here, expert opinion and the use of more data for
20 seconds as a time frame for a respiration segment for statistical treatment could make the decision making process
analyzing the data and classifying the episodes into apnea, even more robust.
normal breath or body movements. The algorithm is also run
2820
Figure 6. Real-time detection of i) body movement artifacts (shown by
low-amplitude (~50) horizontal dashed line for a duration of 15-35
Figure 5. Detection of the onset of body movements (after seconds, and ii) apnea (shown by high amplitude (~200) horizontal
around 10 seconds). Detection of the episodes with body dashed line for a duration of 75-95 seconds).
movements is signified by horizontal dashed line with non-zero
amplitude. REFERENCES
[1] P. Varady ; T. Micsik ; S. Benedek ; Z. Benyo, “A novel method for
the detection of apnea and hypopnea events in respiration signals.”,
As Fig. 5 illustrates, the proposed algorithm is capable of IEEE Trans.Biomedical Eng., Volume: 49, Issue: 9, Sept. 2002.
separating episodes of healthy breathing from episodes with [2] C. Guilleminault; A. Tilkian; W. C. Dement, “The Sleep Apnea
significant disturbances of body movement. The results were Syndromes”, Annual review of medicine, 1976, 27(1), 465-484.
[3] T. Young; L. Evans; L. Finn;M Palta, “Estimation of the clinically
agreeable with human experts. In Fig. 6, we can see that the diagnosed proportion of sleep apnea syndrome in middle-aged men
algorithm is capable of detecting apnea and body movement. and women.” Sleep, 1997, 20, 705–706. Medline.
[4] T. Ning and J. D. Bronzino, "Autoregressive and bispectral analysis
The performance of our approach was also validated techniques: EEG applications," Special Issue on Biomedical Signal
using the PhysioBank MIT database [10]. We used both Processing for IEEE Engineering in Medicine and Biology Magazine,
healthy breathing and apnea episodes. The algorithm was Vol.9, No.1, pp.47-50, March 1990.
successful in detecting all apnea episodes as shown in Fig.7. [5] K. Nepal ; E. Biegeleisen ; T. Ning, “Apnea detection and respiration
rate estimation through parametric modelling.”, Bioengineering
Conference, Proceedings of the IEEE 28th Annual Northeast, 2002
[6] Farah Q Al-Khalidi, Reza Saatchi, Derek Burke, Heather E Elphick,
V. CONCLUSION Stephen Tan. Respiration Rate Monitoring Methods: A Review.
Pediatric Pulmonology, Wiley, 2011, 46 (6), pp.523.
This paper demonstrates the performance of a new [7] L.A. Wallis; M. Healy; M.B. Undy, I. Maconochie. “Age related
respiration monitoring system. In absence of the apnea reference ranges for respiration rate and heart rate from 4 to 16 years.”
episodes, our algorithm was able to accurately estimate the Arch Dis Child, 2005;90:1117-21.
respiration rate. Our results have shown that respiratory [8] M. Nishyama; M. Miyamoto; K. Watanabe, “Respiration and body
signal features extracted from multiple signal processing movement analysis during sleep in bed using hetero-core fiber optic
pressure sensors without constraint to human activity.” J. Biomed.
methods can be effectively analyzed in real time using a Opt. 2011, Volume 16, Issue 1.
fuzzy logic-based expert system to correctly categorize [9] L. A. Zahed, “Fuzzy Sets”, Information and Control, 1965, volume 8,
respiratory signals into normal breathing, breathing with 338-358
motion artifacts, and apnea. [10] A.L. Goldberger, L.A.N. Amaral, L Glass, et al.“PhysioBank,
PhysioToolkit, and PhysioNet: Components of a New Research
Resource for Complex Physiologic Signals.” Circulation 101(23),
2014, e215-e220
Figure 7. Detection of normal breathing (left) and detection of apnea (right) for signal collected from MIT online database [10]. Discussed
algorithm shifts the horizontal dashed line from amplitude of 0 to 1.5 when it detects apnea, as shown above.
2821